Login / Signup
Q-Learning with Dynamic Rewards Table Applied to the SONET/SDH Ring Problem.
Thiago Henrique Freire de Oliveira
Adrião Duarte Dória Neto
Jorge Dantas de Melo
Published in:
IJCNN (2018)
Keyphrases
</>
reinforcement learning
learning algorithm
dynamic environments
cooperative
single chip
database
state space
real time
neural network
decision making
markov decision processes